{"id":"https://openalex.org/W7124867973","doi":"https://doi.org/10.1109/asew67777.2025.00018","title":"Bridging LLM Planning Agents and Formal Methods: A Case Study in Plan Verification","display_name":"Bridging LLM Planning Agents and Formal Methods: A Case Study in Plan Verification","publication_year":2025,"publication_date":"2025-11-16","ids":{"openalex":"https://openalex.org/W7124867973","doi":"https://doi.org/10.1109/asew67777.2025.00018"},"language":"en","primary_location":{"id":"doi:10.1109/asew67777.2025.00018","doi":"https://doi.org/10.1109/asew67777.2025.00018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asew67777.2025.00018","pdf_url":null,"source":{"id":"https://openalex.org/S7407086215","display_name":"IEEE/ACM International Conference on Automated Software Engineering Workshops (ASEW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 40th IEEE/ACM International Conference on Automated Software Engineering Workshops (ASEW)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.03469","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091312735","display_name":"Keshav Ramani","orcid":"https://orcid.org/0000-0003-1606-2065","observed_orcids":["https://orcid.org/0000-0003-1606-2065"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keshav Ramani","raw_affiliation_strings":["J.P. Morgan AI Research,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"J.P. Morgan AI Research,New York,USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007634904","display_name":"Vali Tawosi","orcid":"https://orcid.org/0000-0001-5052-672X","observed_orcids":["https://orcid.org/0000-0001-5052-672X"]},"institutions":[{"id":"https://openalex.org/I4210110280","display_name":"J.P. Morgan","ror":"https://ror.org/01sxmq816","country_code":"GB","type":"other","lineage":["https://openalex.org/I4210110280"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Vali Tawosi","raw_affiliation_strings":["J.P. Morgan AI Research,London,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"J.P. Morgan AI Research,London,UK","institution_ids":["https://openalex.org/I4210110280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082203057","display_name":"Salwa Alamir","orcid":"https://orcid.org/0009-0006-6650-7041","observed_orcids":["https://orcid.org/0009-0006-6650-7041"]},"institutions":[{"id":"https://openalex.org/I4210110280","display_name":"J.P. Morgan","ror":"https://ror.org/01sxmq816","country_code":"GB","type":"other","lineage":["https://openalex.org/I4210110280"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Salwa Alamir","raw_affiliation_strings":["J.P. Morgan AI Research,London,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"J.P. Morgan AI Research,London,UK","institution_ids":["https://openalex.org/I4210110280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050512952","display_name":"Daniel Borrajo","orcid":"https://orcid.org/0000-0001-5282-0463","observed_orcids":["https://orcid.org/0000-0001-5282-0463"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Borrajo","raw_affiliation_strings":["J.P. Morgan AI Research,Madrid,Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"J.P. Morgan AI Research,Madrid,Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.2366,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.98115841,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.7035999894142151,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.7035999894142151,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.17640000581741333,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.08900000154972076,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/plan-verification","display_name":"plan verification","score":0.8429999947547913},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.777999997138977},{"id":"https://openalex.org/keywords/kripke-structures","display_name":"Kripke structures","score":0.7559999823570251},{"id":"https://openalex.org/keywords/linear-temporal-logic","display_name":"linear temporal logic","score":0.9649999737739563},{"id":"https://openalex.org/keywords/model-checking","display_name":"model checking","score":0.984000027179718},{"id":"https://openalex.org/keywords/formal-verification","display_name":"formal verification","score":0.7059999704360962},{"id":"https://openalex.org/keywords/gpt-5","display_name":"GPT-5","score":0.7799999713897705}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7702000141143799},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7444999814033508},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.5769000053405762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5212000012397766},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C146072743","wikidata":"https://www.wikidata.org/wiki/Q192161","display_name":"Formal language","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4237000048160553},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.39579999446868896},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.37459999322891235},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3598000109195709},{"id":"https://openalex.org/C95318506","wikidata":"https://www.wikidata.org/wiki/Q6588467","display_name":"Textual entailment","level":3,"score":0.35679998993873596},{"id":"https://openalex.org/C4777664","wikidata":"https://www.wikidata.org/wiki/Q1536492","display_name":"Linear temporal logic","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.34610000252723694},{"id":"https://openalex.org/C75606506","wikidata":"https://www.wikidata.org/wiki/Q1049183","display_name":"Formal methods","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.33899998664855957},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3188000023365021},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3098999857902527},{"id":"https://openalex.org/C2775940519","wikidata":"https://www.wikidata.org/wiki/Q17067742","display_name":"Logic model","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C102993220","wikidata":"https://www.wikidata.org/wiki/Q387196","display_name":"Description logic","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C116253237","wikidata":"https://www.wikidata.org/wiki/Q1437424","display_name":"Formal specification","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2623000144958496}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/asew67777.2025.00018","doi":"https://doi.org/10.1109/asew67777.2025.00018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asew67777.2025.00018","pdf_url":null,"source":{"id":"https://openalex.org/S7407086215","display_name":"IEEE/ACM International Conference on Automated Software Engineering Workshops (ASEW)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 40th IEEE/ACM International Conference on Automated Software Engineering Workshops (ASEW)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.03469","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.03469","pdf_url":"https://arxiv.org/pdf/2510.03469","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.03469","doi":"https://doi.org/10.48550/arxiv.2510.03469","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.03469","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.03469","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.03469","pdf_url":"https://arxiv.org/pdf/2510.03469","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1529693658","https://openalex.org/W1574030932","https://openalex.org/W1835682006","https://openalex.org/W2023808162","https://openalex.org/W2919200352","https://openalex.org/W3126881288","https://openalex.org/W3144889436","https://openalex.org/W4401567960","https://openalex.org/W4405103253","https://openalex.org/W4409779994","https://openalex.org/W4411234014","https://openalex.org/W7124866172"],"related_works":["https://openalex.org/W4411119964","https://openalex.org/W4412886640","https://openalex.org/W7220230041","https://openalex.org/W7166658681","https://openalex.org/W7222929444","https://openalex.org/W4414977039","https://openalex.org/W4417098730","https://openalex.org/W4412944606","https://openalex.org/W4409779994","https://openalex.org/W4402366785"],"abstract_inverted_index":{"We":[0,37],"introduce":[1],"a":[2,43],"novel":[3],"framework":[4,41],"for":[5,100],"evaluating":[6],"the":[7,47,90],"alignment":[8],"between":[9],"natural":[10],"language":[11],"plans":[12],"and":[13,23,33,52,60],"their":[14],"expected":[15],"behavior":[16],"by":[17],"converting":[18],"them":[19],"into":[20],"Kripke":[21],"structures":[22],"Linear":[24],"Temporal":[25],"Logic":[26],"(LTL)":[27],"using":[28],"Large":[29],"Language":[30],"Models":[31],"(LLMs)":[32],"performing":[34],"model":[35],"checking.":[36],"systematically":[38],"evaluate":[39],"this":[40],"on":[42,54],"simplified":[44],"version":[45],"of":[46,74,92],"PlanBench":[48],"plan":[49],"verification":[50],"dataset":[51],"report":[53],"metrics":[55],"like":[56],"Accuracy,":[57],"Precision,":[58],"Recall":[59],"F1":[61],"scores.":[62],"Our":[63],"experiments":[64],"demonstrate":[65],"that":[66,84],"GPT-5":[67],"achieves":[68],"excellent":[69],"classification":[70],"performance":[71],"(F1":[72],"score":[73],"96.3%)":[75],"while":[76],"almost":[77],"always":[78],"producing":[79],"syntactically":[80],"perfect":[81,94],"formal":[82,95],"representations":[83],"can":[85],"act":[86],"as":[87],"guarantees.":[88],"However,":[89],"synthesis":[91],"semantically":[93],"models":[96],"remains":[97],"an":[98],"area":[99],"future":[101],"exploration.":[102]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2026-01-21T00:00:00"}